Content
57%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is well-organized and mostly lean with concrete, runnable commands, but it is held back by a missing bundle script, a vague parameter step, and the absence of validation checkpoints in a batch-extraction workflow.
Suggestions
Add an explicit validation checkpoint to the workflow (e.g., after Step 2 confirm the schema returned, after Step 4 verify the output file is non-empty) with a fix-and-retry loop.
Resolve the missing reference: either bundle reference/scripts/run_actor.js in the skill or replace the command with self-contained, inline executable steps.
Make Step 3 concrete by specifying default result counts per use case instead of "Based on character of use case".
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes Claude's competence, with no padding or explanations of concepts Claude already knows; the large Actor-selection table is actionable reference data rather than fluff, leaving only minor tightening opportunities, so it sits above the midpoint but below a perfectly lean 5. | 4 / 5 |
Actionability | Provides concrete bash commands with real Actor IDs and copy-paste flags (--actor, --input, --output, --format), but Step 4's commands reference ${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js which is not present in the bundle, and Step 3's "Number of results: Based on character of use case" is vague, leaving key execution details incomplete. | 3 / 5 |
Workflow Clarity | A clear 5-step checklist sequences the process, but this is a batch data-extraction operation with no explicit validation/verification checkpoint (e.g., confirm the schema fetch succeeded, verify output non-empty) or validate-fix-retry loop, so per the batch-operation cap workflow clarity cannot exceed 3. | 3 / 5 |
Progressive Disclosure | The single SKILL.md is organized into clear sections but the only external reference (run_actor.js) is buried inside a bash command rather than clearly signaled, and no references/scripts/assets bundle files exist, so structure is present but not well split or navigable. | 3 / 5 |
Total | 13 / 20 Passed |